Supply chains operating across global networks are increasingly exposed to recurring weather disruptions that inflate transportation lead times in predictable spatial and temporal patterns; however, most fulfillment frameworks treat these disruptions as random events and fail to leverage their seasonal recurrence for proactive planning. This capstone develops a weather-aware optimization framework that quantifies recurring weather risk and embeds it into supply chain fulfillment decisions. Using climate data and U.S. airport performance records, weather disruption probabilities are modeled and translated into lead time variability estimates across truck and air segments, as well as terminal nodes. A Mixed-Integer Linear Programming model compares a risk-agnostic Baseline policy with a Risk-Aware policy that jointly minimizes expected lead time and its standard deviation, evaluated through Monte Carlo simulation over 22,125 orders. The results show that the Risk-Aware policy reduces late orders by 63.8%—from 127 to 46—providing quantitative evidence that incorporating spatio-temporal weather risk into fulfillment decisions meaningfully improves service reliability. The analysis further reveals a seasonal concentration of disruption risk, with January and February accounting for a disproportionate share of late orders, suggesting that targeted Risk-Aware fulfillment during high-risk months can yield substantial reliability gains without incurring unnecessary lead time overhead year-round.
